The Elements of Statistical Learning | T. Hastie, R. Tibshirani, ...

The Elements of Statistical Learning | T. Hastie, R. Tibshirani, ... | The Elements of Statistical Learning

books:

The Elements of St...

	The Elements of Statistical Learning T. Hastie, R. Tibshirani, ... Springer, 2003 - 552 pages average customer review:based on 27 reviews view larger image
	for more information click here

highly recommended

One of the Essential Books on Modern Machine Learning

This book is a miracle of clarity and comprehensiveness. It presents a unified approach to state of the art machine learning techniques from a statistical perspective. The layout is logical and the level of math is appropriate for applications-oriented engineers and computer scientists, as well as theorists. Sections where the book does need to go into heavier mathematics are clearly marked and generally optional. I found the book very easy to read, but at the same time very comprehensive.

The book provides a very illuminating counterpoint to other books that promote the Computational Learning Theory (COLT / kernels / large margins) viewpoint of modern machine learning. Many of the same techniques such as boosting and support vector machines are discussed, but are motivated in different ways. Appropriate regularization is seen as the key to avoiding overfitting with complex models, rather than margin maximization. Mathematically you often end up solving the same problem, but personally I usually find the statistical approach much more direct and intuitive.

This book is a nice follow on to introductory pattern recognition texts such as Duda and Hart, though it can be read without any prior pattern recognition knowledge. It provides a nice mix of theory and paractical algorithms, illustrated with numerous examples. An essential element of your machine learning library!

for more information click here

The Elements of Statistical Learning

The book is written by some of the biggest names currently in the field, and thus is written at a certain level, this isn't a fault of the book or the authers, but rather it was written for a specific audience. However I did find it odd when they would occassionally explain basic readily known notation, but later on assume the reader is familiar with what I would regard as advanced notation, or leave out quite a few steps in their mathematics assuming the reader understands what they did. This book covers a wide range of techniques ranging from the more traditional to the current, and for each topic presents an overview of the technique and provides adequate references for further exploration.

The reader should have a good underlying understanding of linear algebra, statistics and probability theory and also be familiar with the techniques presented here. This book was used in a graduate engineering data mining class, and most of us struggled greatly with the book. This book probably would have been more appropriate if this was a book to augment another text, or if this had not been the first time we had seen topics such as those presented, this being the book to explain neural networks, support vector machines and whatnot when you've never seen them before makes for a very bewildering experience, but once you find a few journal articles the techniques actually are fairly easy to understand.

The book does not explain how to implement using software any of the techniques, this is a topic left up to other books, such as Modern Applied Statistics with S by Ripley and Venerables, and only in their discussion about apriori for association rules did I see that they state a software package. It would have been nice if they would have given some insight into how they created some of the great graphics that punctuate the book, perhaps as additional material on the website.

A book that is more down to earth for engineers, albeit different in scope, would be Duda and Hart's Pattern Classification, which I believe are electrical engineers and written more from an engineering standpoint. In addition the Duda and Hard book gives a lot of applications-based problems and has an associated MATLAB handbook to walk readers through building many types of learners, while this book the end-of-chapter excercises are almost exclusively proofs and theoretical excercises. Not a fault of the book, but rather just a difference and depends on what the reader wants to get out of it.

Ultimately, even though it did prove to be a rather confusing book, I have learned a lot from it and will continue to go through it to learn even more from it as it does tend to become more lucid the more I go through it.

for more information click here

reviews: 1, 2, 3, page 4, 5, 6

products you might be interested in

recommendations

Statistical Learning and Optimization
Carnegie Mellon Statistics Textbooks
Computational Finance
Machine Learning
Machine Learning